AI Paper Atlas

Research map / Learning theory and algorithms / Clustering

K-Medoids For K-Means Seeding

James Newling, François Fleuret

NeurIPS 2017 · Learning theory and algorithms › Clustering · approach: k-means++ seeding analysis · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use CLARANS instead of k-means++ for initializationLloyd k-means · 23 datasetsinitialization MSE: 30 %Improved
Use CLARANS instead of k-means++ for initializationLloyd k-means · 23 datasetsfinal minimum MSE: 3 %Improved
Use CLARANS swaps rather than medlloyd Voronoi iterationK-medoids · synthetic and real datasetsenergyImproved
Add CLARANS after k-means++ initializationLloyd k-means · complete RNA datasetmean final MSE: 0.83 -> 0.76Improved
Add CLARANS before Lloyd without k-means++ pre-initializationLloyd k-means · complete RNA datasetmean final MSE: 0.83 -> 0.76Improved
Replace k-means++ initialization with MCMC initializationLloyd k-means · 23 datasetsinitialization MSENo clear effect
Replace uniform initialization with k-means++Lloyd k-means · 23 datasetsinitialization and final MSEImproved
Replace uniform initialization with the bf schemeLloyd k-means · 23 datasetsfinal MSENo clear effect
Use optimization level 2 rather than level -2 (ablation)CLARANS · simulation data, σ = 2⁻⁴log₂(distance calculations): 44.1 -> 26.7Improved
Use optimization level 2 rather than level 0 (ablation)CLARANS · simulation data, σ = 2⁻⁴time [s]: 407 -> 15.6Improved
Add level 3 subsampling to exact CLARANS accelerations (ablation)CLARANS · N = 500,000, d = 4, K = 500 Gaussian dataconvergence time: within 20 secondsImproved
Pre-initialize CLARANS with k-means++ (ablation)CLARANS + Lloyd · complete RNA datasetmean final MSE: 0.76 -> 0.76No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy